Related papers: Stochastic Prediction of Multi-Agent Interactions …

Multivariate time series forecasting enables the prediction of future states by leveraging historical data, thereby facilitating decision-making processes. Each data node in a multivariate time series encompasses a sequence of multiple…

We apply recent methods in stochastic data analysis for discovering a set of few stochastic variables that represent the relevant information on a multivariate stochastic system, used as input for artificial neural networks models for air…

Inference on unknown quantities in dynamical systems via observational data is essential for providing meaningful insight, furnishing accurate predictions, enabling robust control, and establishing appropriate designs for future…

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of…

Natural physical, chemical, and biological dynamical systems are often complex, with heterogeneous components interacting in diverse ways. We show how simple graph neural networks can be designed to jointly learn the interaction rules and…

This paper addresses the limitations of multi-node perception and delayed scheduling response in distributed systems by proposing a GNN-based multi-node collaborative perception mechanism. The system is modeled as a graph structure.…

We present an approach for building an active agent that learns to segment its visual observations into individual objects by interacting with its environment in a completely self-supervised manner. The agent uses its current segmentation…

The Information Bottleneck theory provides a theoretical and computational framework for finding approximate minimum sufficient statistics. Analysis of the Stochastic Gradient Descent (SGD) training of a neural network on a toy problem has…

Stochastic networks are a plausible representation of the relational information among entities in dynamic systems such as living cells or social communities. While there is a rich literature in estimating a static or temporally invariant…

Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two…

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects.…

We present a new algorithm for predicting the near-term trajectories of road-agents in dense traffic videos. Our approach is designed for heterogeneous traffic, where the road-agents may correspond to buses, cars, scooters, bicycles, or…

This work leverages adaptive social learning to estimate partially observable global states in multi-agent reinforcement learning (MARL) problems. Unlike existing methods, the proposed approach enables the concurrent operation of social…

In order to explore and act autonomously in an environment, an agent needs to learn from the sensorimotor information that is captured while acting. By extracting the regularities in this sensorimotor stream, it can learn a model of the…

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model. Here we introduce a new…

This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes. The proposed algorithm uses a variational autoencoder to…

In this work, we explore the state-space formulation of a network process to recover, from partial observations, the underlying network topology that drives its dynamics. To do so, we employ subspace techniques borrowed from system…

In this paper, we propose a new procedure for unconditional and conditional forecasting in agent-based models. The proposed algorithm is based on the application of amortized neural networks and consists of two steps. The first step…

Research in transportation frequently involve modelling and predicting attributes of events that occur at regular intervals. The event could be arrival of a bus at a bus stop, the volume of a traffic at a particular point, the demand at a…

Theories for visually guided action account for online control in the presence of reliable sources of visual information, and predictive control to compensate for visuomotor delay and temporary occlusion. In this study, we characterize the…